AI and Cancer Research ── 2026-10-20
New papers on cancer and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 13 themes, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.
Read by cancer type: Cancer biology（2） · Breast（0） · Lung（0） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（0） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（1） · Kidney（1） · Bladder（0）
Cancer molecular biology and AI
- Abstract
Nature Biomedical Engineering, Published online: 19 October 2026; doi:10.1038/s41551-026-01803-7 An interpretable neural network, SPACER, learns the rules of cellular recruitment directly from tissue spatial transcriptomics data. Analyses of multiple cancers reveal a role for the local antigen presentation machinery and tumour mucins in T cell recruitment to tumours, and a mouse model of severe checkpoint inhibitor-induced myocarditis identifies CD4+ T cells as key disease effectors.
Journal IF-equivalent: 15.4 (OpenAlex 2-year mean citedness, value as of 2026-10-19, retrieved 2026-10-20; not the official Clarivate IF)Reference: [No authors listed]. An interpretable AI model decodes the rules of cell recruitment to specific destinations. Nat Biomed Eng. 2026 Oct 19 [Epub ahead of print]. doi:10.1038/s41551-026-01803-7.Checked: Abstract only - Abstract
Genomic association and predictive modeling often operate in high-dimensional regimes where the number of candidate genes far exceeds the number of study subjects, making inference prone to instability and sensitive to missing values, batch effects, and sparse signals. Meanwhile, biology provides rich relational context (protein interactions, pathway co-membership, regulatory targeting, and more) that encodes functional relationships between genes. The recent success of deep learning has demonstrated effective model designs for integrating heterogeneous directed and symmetric relationships into a compact unified representation. Existing methods that leverage graph-based representations of biological knowledge fall along several axes: some use them as input for deep learning models with predictive modules that generate outcome predictions for supervised tasks; others learn general-purpose numerical representation (embeddings) of genes for use in downstream analysis; and a separate line of research constructs regularization priors from the biological sources tailored to a specific application. To the best of our knowledge, no prior work has trained a model to integrate multiple biological sources by learning their relative reliability to build a task-agnostic Laplacian-based smoothness prior for epidemiological inference. We introduce a framework that fuses complementary biological networks into a single symmetric gene-gene coupling matrix via a Heterogeneous Graph Attention Network (HGAT), creating a reusable prior that can regularize any model with gene-indexed parameters. We first perform an intrinsic methodological validation of the approach against multiple benchmark models to assess the embeddings and output graph quality. Through controlled simulation we establish that a faithful prior must capture multi-hop functional coherence rather than direct edges alone, and that the value of learning lies specifically in the adaptive, reliability-weighted fusion of incomplete, heterogeneous sources, where fixed kernels and uniformly-weighted linear baselines fall short. We further validate that the learned prior generalizes by preserving graded biological similarity on regulatory sources held out from training, maintains competitive performance in downstream cancer prediction, and demonstrates a concrete practical advantage in a niche, under-annotated regulatory application where generalization matters. The resulting prior offers transparent biological provenance and proven generalization by integrating fragmented biological knowledge into convex inference without sacrificing predictive performance.
Journal IF-equivalent: 4.8 (OpenAlex 2-year mean citedness, value as of 2026-10-19, retrieved 2026-10-20; not the official Clarivate IF)Reference: Origgi JM, Zeegers M, Mehrkanoon S, von Moltke C, Wesselius A, Nattino G. Genes2Reg: Constructing a biologically-faithful gene coupling prior via deep adaptive fusion of heterogeneous knowledge sources. BMC Bioinformatics. 2026 Oct 17 [Epub ahead of print]. doi:10.1186/s12859-026-06655-1.Checked: Abstract only
See all 2 Cancer biology papers →
Breast cancer: treatment, trials and AI
No new qualifying paper for this issue.
Lung cancer: treatment, trials and AI
No new qualifying paper for this issue.
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
No new qualifying paper for this issue.
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
No new qualifying paper for this issue.
Ovarian cancer: treatment, trials and AI
No new qualifying paper for this issue.
Endometrial cancer: treatment, trials and AI
No new qualifying paper for this issue.
Gastric cancer: treatment, trials and AI
No new qualifying paper for this issue.
Liver cancer: treatment, trials and AI
- Abstract
Host-related imaging phenotypes beyond conventional muscle and fat measurements remain insufficiently explored in hepatocellular carcinoma (HCC). This study evaluated associations between abdominal organ features and outcomes in 1512 patients with HCC receiving immune checkpoint inhibitor-based therapy across 10 cohorts from six centers. Deep learning automatically quantified nine abdominal organs from pretreatment CT or MR images, yielding 18 volume and height-normalized indices. Continuous organ measurements were assessed using multivariable Cox regression with Benjamini–Hochberg false discovery rate correction; exploratory external validation used WHUH-derived median cutoffs. The primary outcomes were overall survival (OS) and progression-free survival (PFS). In the primary analysis, organ measurements were evaluated as continuous variables using multivariable Cox regression, followed by Benjamini–Hochberg false discovery rate (FDR) correction. Exploratory external validation used median cut-offs derived from the WHUH cohort and fixed in the remaining centers. Liver volume, left adrenal gland volume, and right kidney index were associated with overall survival after FDR correction. No continuous organ metric remained significant for progression-free survival, whereas higher right kidney volume and right kidney index were associated with shorter progression-free survival in exploratory external validation. Automated multi-organ quantification from routine imaging may provide complementary prognostic information without requiring additional examinations or radiation exposure.
Journal IF-equivalent: 8.9 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)Reference: Li T, Fu X, Guo Y, Wang N, Li S, Guo X, et al. AI-driven quantitative assessment of abdominal organs and immunotherapy outcomes across multicenter hepatocellular carcinoma cohorts. npj Precis Onc. 2026 Oct 17 [Epub ahead of print]. doi:10.1038/s41698-026-01739-w.Checked: Abstract only
Kidney cancer: treatment, trials and AI
- Abstract
PURPOSE: This study aims to assess the computed tomography (CT) features of transcription factor E3 gene fusion renal cell carcinoma (TFE3-RCC) and develop a radiomics-based model for preoperative discrimination between TFE3-RCCs and clear cell renal cell carcinomas (ccRCCs). METHODS: A total of 34 pathologically confirmed TFE3-RCC and 98 ccRCC cases with preoperative renal CT were enrolled. Subjective image analysis was performed to determine the CT parameters that can distinguish TFE3-RCCs from ccRCCs. A random forest classifier was evaluated through 5-fold cross-validation to establish the radiomics model. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve analysis. RESULTS: Patients with TFE3-RCC were significantly younger (36.2 ± 14.4 vs. 56.8 ± 13.5 years, P < 0.001). Ten of the 34 TFE3-RCCs had calcification, whereas only four in the ccRCC group did (29.4% vs. 4.1%, P < 0.001). Additionally, the TOC enhancement ratio in the corticomedullary phase were significantly lower in the TFE3-RCC group compared with the ccRCC group (0.61 ± 0.11 vs. 0.90 ± 0.13, p < 0.001). The random forest classifier achieved stable performance with robust cross-validation metrics (AUC = 0.82 ± 0.17, accuracy = 85% ± 13%). CONCLUSION: The CT radiomics model exhibits favorable diagnostic performance for noninvasively differentiating TFE3-RCC from ccRCC, supporting its potential utility in preoperative personalized management of renal masses.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-09, retrieved 2026-10-10; not the official Clarivate IF)Reference: Liu Y, Wang K, Zhang Y, Liu J, Xi Z, Wang X, et al. Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model. BMC Cancer. 2026 Jul 22;26(1):1247. doi:10.1186/s12885-026-16463-8.Checked: Abstract only
Bladder cancer: treatment, trials and AI
No new qualifying paper for this issue.